The Tractability Landscape of Sampling with Inexact Scores

Abstract:We provide a simple and tight characterization of the types of inexact score oracle access that permit sampling with vanishing total variation bias, for a standard, well-behaved target family. Our main result shows that any weaker error than the sub-Gaussian assumption used by [YW26] rules out the tractability of unbiased sampling. This strengthens the conclusion of [CCSW26] to be algorithm-agnostic, and to hold for a wider range of error assumptions.

Machine Learning (stat.ML); Machine Learning (cs.LG); Statistics Theory (math.ST)

arXiv:2607.19004 [stat.ML]

(or arXiv:2607.19004v1 [stat.ML] for this version)

https://doi.org/10.48550/arXiv.2607.19004 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.